openfin-onchain

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill searches and processes token metadata and search results from external token registries via /token/search, which is a low-risk active search path.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill documents direct financial transfer and swap operations (POST /agent/onchain/send, onchain_jupiter_order, and onchain_jupiter_execute) which execute blockchain transfers and token swaps using API keys (x-api-key). Although safety checklists and user confirmation prompts are instructed, these depend entirely on the agent following text guidelines rather than independent service-side authentication or authorization checking the destination or amount. Therefore, it constitutes a direct financial operation without qualifying independent access control.